Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14542
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation related to formal equations or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX math mode

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    」
    -1.09
    ”.
    -0.95
    ”,
    -0.95
    ”
    -0.94
    」、「
    -0.92
    ".$
    -0.86
    ”、“
    -0.86
    ";
    
    -0.86
    ",
    -0.85
    ”。
    -0.82
    POSITIVE LOGITS
    </h5>
    1.08
    </h6>
    0.99
    IsMutable
    0.92
     дописавши
    0.88
    AddTagHelper
    0.88
    Geplaatst
    0.81
    </h3>
    0.79
    Tembelea
    0.76
     referenties
    0.76
    ContentAsync
    0.76
    Activations Density 1.136%

    No Known Activations